inet_diag.c

linux 内核源代码

/*
 * inet_diag.c	Module for monitoring INET transport protocols sockets.
 *
 * Version:	$Id: inet_diag.c,v 1.3 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Alexey Kuznetsov, <[e-mail]>
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/random.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/time.h>

#include <net/icmp.h>
#include <net/tcp.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/inet6_hashtables.h>
#include <net/netlink.h>

#include <linux/inet.h>
#include <linux/stddef.h>

#include <linux/inet_diag.h>

static const struct inet_diag_handler **inet_diag_table;

struct inet_diag_entry {
	__be32 *saddr;
	__be32 *daddr;
	u16 sport;
	u16 dport;
	u16 family;
	u16 userlocks;
};

static struct sock *idiagnl;

#define INET_DIAG_PUT(skb, attrtype, attrlen) \
	RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))

static DEFINE_MUTEX(inet_diag_table_mutex);

static const struct inet_diag_handler *inet_diag_lock_handler(int type)
{
#ifdef CONFIG_KMOD
	if (!inet_diag_table[type])
		request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
			       NETLINK_INET_DIAG, type);
#endif

	mutex_lock(&inet_diag_table_mutex);
	if (!inet_diag_table[type])
		return ERR_PTR(-ENOENT);

	return inet_diag_table[type];
}

static inline void inet_diag_unlock_handler(
	const struct inet_diag_handler *handler)
{
	mutex_unlock(&inet_diag_table_mutex);
}

static int inet_csk_diag_fill(struct sock *sk,
			      struct sk_buff *skb,
			      int ext, u32 pid, u32 seq, u16 nlmsg_flags,
			      const struct nlmsghdr *unlh)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_diag_msg *r;
	struct nlmsghdr  *nlh;
	void *info = NULL;
	struct inet_diag_meminfo  *minfo = NULL;
	unsigned char	 *b = skb_tail_pointer(skb);
	const struct inet_diag_handler *handler;

	handler = inet_diag_table[unlh->nlmsg_type];
	BUG_ON(handler == NULL);

	nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
	nlh->nlmsg_flags = nlmsg_flags;

	r = NLMSG_DATA(nlh);
	BUG_ON(sk->sk_state == TCP_TIME_WAIT);

	if (ext & (1 << (INET_DIAG_MEMINFO - 1)))
		minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo));

	if (ext & (1 << (INET_DIAG_INFO - 1)))
		info = INET_DIAG_PUT(skb, INET_DIAG_INFO,
				     handler->idiag_info_size);

	if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) {
		const size_t len = strlen(icsk->icsk_ca_ops->name);

		strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1),
		       icsk->icsk_ca_ops->name);
	}

	r->idiag_family = sk->sk_family;
	r->idiag_state = sk->sk_state;
	r->idiag_timer = 0;
	r->idiag_retrans = 0;

	r->id.idiag_if = sk->sk_bound_dev_if;
	r->id.idiag_cookie[0] = (u32)(unsigned long)sk;
	r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);

	r->id.idiag_sport = inet->sport;
	r->id.idiag_dport = inet->dport;
	r->id.idiag_src[0] = inet->rcv_saddr;
	r->id.idiag_dst[0] = inet->daddr;

#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	if (r->idiag_family == AF_INET6) {
		struct ipv6_pinfo *np = inet6_sk(sk);

		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
			       &np->rcv_saddr);
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
			       &np->daddr);
	}
#endif

#define EXPIRES_IN_MS(tmo)  DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)

	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
		r->idiag_timer = 1;
		r->idiag_retrans = icsk->icsk_retransmits;
		r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
		r->idiag_timer = 4;
		r->idiag_retrans = icsk->icsk_probes_out;
		r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
	} else if (timer_pending(&sk->sk_timer)) {
		r->idiag_timer = 2;
		r->idiag_retrans = icsk->icsk_probes_out;
		r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires);
	} else {
		r->idiag_timer = 0;
		r->idiag_expires = 0;
	}
#undef EXPIRES_IN_MS

	r->idiag_uid = sock_i_uid(sk);
	r->idiag_inode = sock_i_ino(sk);

	if (minfo) {
		minfo->idiag_rmem = atomic_read(&sk->sk_rmem_alloc);
		minfo->idiag_wmem = sk->sk_wmem_queued;
		minfo->idiag_fmem = sk->sk_forward_alloc;
		minfo->idiag_tmem = atomic_read(&sk->sk_wmem_alloc);
	}

	handler->idiag_get_info(sk, r, info);

	if (sk->sk_state < TCP_TIME_WAIT &&
	    icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
		icsk->icsk_ca_ops->get_info(sk, ext, skb);

	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
	return skb->len;

rtattr_failure:
nlmsg_failure:
	nlmsg_trim(skb, b);
	return -EMSGSIZE;
}

static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
			       struct sk_buff *skb, int ext, u32 pid,
			       u32 seq, u16 nlmsg_flags,
			       const struct nlmsghdr *unlh)
{
	long tmo;
	struct inet_diag_msg *r;
	const unsigned char *previous_tail = skb_tail_pointer(skb);
	struct nlmsghdr *nlh = NLMSG_PUT(skb, pid, seq,
					 unlh->nlmsg_type, sizeof(*r));

	r = NLMSG_DATA(nlh);
	BUG_ON(tw->tw_state != TCP_TIME_WAIT);

	nlh->nlmsg_flags = nlmsg_flags;

	tmo = tw->tw_ttd - jiffies;
	if (tmo < 0)
		tmo = 0;

	r->idiag_family	      = tw->tw_family;
	r->idiag_state	      = tw->tw_state;
	r->idiag_timer	      = 0;
	r->idiag_retrans      = 0;
	r->id.idiag_if	      = tw->tw_bound_dev_if;
	r->id.idiag_cookie[0] = (u32)(unsigned long)tw;
	r->id.idiag_cookie[1] = (u32)(((unsigned long)tw >> 31) >> 1);
	r->id.idiag_sport     = tw->tw_sport;
	r->id.idiag_dport     = tw->tw_dport;
	r->id.idiag_src[0]    = tw->tw_rcv_saddr;
	r->id.idiag_dst[0]    = tw->tw_daddr;
	r->idiag_state	      = tw->tw_substate;
	r->idiag_timer	      = 3;
	r->idiag_expires      = DIV_ROUND_UP(tmo * 1000, HZ);
	r->idiag_rqueue	      = 0;
	r->idiag_wqueue	      = 0;
	r->idiag_uid	      = 0;
	r->idiag_inode	      = 0;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	if (tw->tw_family == AF_INET6) {
		const struct inet6_timewait_sock *tw6 =
						inet6_twsk((struct sock *)tw);

		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
			       &tw6->tw_v6_rcv_saddr);
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
			       &tw6->tw_v6_daddr);
	}
#endif
	nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail;
	return skb->len;
nlmsg_failure:
	nlmsg_trim(skb, previous_tail);
	return -EMSGSIZE;
}

static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
			int ext, u32 pid, u32 seq, u16 nlmsg_flags,
			const struct nlmsghdr *unlh)
{
	if (sk->sk_state == TCP_TIME_WAIT)
		return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
					   skb, ext, pid, seq, nlmsg_flags,
					   unlh);
	return inet_csk_diag_fill(sk, skb, ext, pid, seq, nlmsg_flags, unlh);
}

static int inet_diag_get_exact(struct sk_buff *in_skb,
			       const struct nlmsghdr *nlh)
{
	int err;
	struct sock *sk;
	struct inet_diag_req *req = NLMSG_DATA(nlh);
	struct sk_buff *rep;
	struct inet_hashinfo *hashinfo;
	const struct inet_diag_handler *handler;

	handler = inet_diag_lock_handler(nlh->nlmsg_type);
	if (!handler)
		return -ENOENT;

	hashinfo = handler->idiag_hashinfo;
	err = -EINVAL;

	if (req->idiag_family == AF_INET) {
		sk = inet_lookup(hashinfo, req->id.idiag_dst[0],
				 req->id.idiag_dport, req->id.idiag_src[0],
				 req->id.idiag_sport, req->id.idiag_if);
	}
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	else if (req->idiag_family == AF_INET6) {
		sk = inet6_lookup(hashinfo,
				  (struct in6_addr *)req->id.idiag_dst,
				  req->id.idiag_dport,
				  (struct in6_addr *)req->id.idiag_src,
				  req->id.idiag_sport,
				  req->id.idiag_if);
	}
#endif
	else {
		goto unlock;
	}

	err = -ENOENT;
	if (sk == NULL)
		goto unlock;

	err = -ESTALE;
	if ((req->id.idiag_cookie[0] != INET_DIAG_NOCOOKIE ||
	     req->id.idiag_cookie[1] != INET_DIAG_NOCOOKIE) &&
	    ((u32)(unsigned long)sk != req->id.idiag_cookie[0] ||
	     (u32)((((unsigned long)sk) >> 31) >> 1) != req->id.idiag_cookie[1]))
		goto out;

	err = -ENOMEM;
	rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
				     sizeof(struct inet_diag_meminfo) +
				     handler->idiag_info_size + 64)),
			GFP_KERNEL);
	if (!rep)
		goto out;

	err = sk_diag_fill(sk, rep, req->idiag_ext,
			   NETLINK_CB(in_skb).pid,
			   nlh->nlmsg_seq, 0, nlh);
	if (err < 0) {
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(rep);
		goto out;
	}
	err = netlink_unicast(idiagnl, rep, NETLINK_CB(in_skb).pid,
			      MSG_DONTWAIT);
	if (err > 0)
		err = 0;

out:
	if (sk) {
		if (sk->sk_state == TCP_TIME_WAIT)
			inet_twsk_put((struct inet_timewait_sock *)sk);
		else
			sock_put(sk);
	}
unlock:
	inet_diag_unlock_handler(handler);
	return err;
}

static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
{
	int words = bits >> 5;

	bits &= 0x1f;

	if (words) {
		if (memcmp(a1, a2, words << 2))
			return 0;
	}
	if (bits) {
		__be32 w1, w2;
		__be32 mask;

		w1 = a1[words];
		w2 = a2[words];

		mask = htonl((0xffffffff) << (32 - bits));

		if ((w1 ^ w2) & mask)
			return 0;
	}

	return 1;
}


static int inet_diag_bc_run(const void *bc, int len,
			    const struct inet_diag_entry *entry)
{
	while (len > 0) {
		int yes = 1;
		const struct inet_diag_bc_op *op = bc;

		switch (op->code) {
		case INET_DIAG_BC_NOP:
			break;
		case INET_DIAG_BC_JMP:
			yes = 0;
			break;
		case INET_DIAG_BC_S_GE:
			yes = entry->sport >= op[1].no;
			break;
		case INET_DIAG_BC_S_LE:
			yes = entry->dport <= op[1].no;
			break;
		case INET_DIAG_BC_D_GE:
			yes = entry->dport >= op[1].no;
			break;
		case INET_DIAG_BC_D_LE:
			yes = entry->dport <= op[1].no;
			break;
		case INET_DIAG_BC_AUTO:
			yes = !(entry->userlocks & SOCK_BINDPORT_LOCK);
			break;
		case INET_DIAG_BC_S_COND:
		case INET_DIAG_BC_D_COND: {
			struct inet_diag_hostcond *cond;
			__be32 *addr;

			cond = (struct inet_diag_hostcond *)(op + 1);
			if (cond->port != -1 &&
			    cond->port != (op->code == INET_DIAG_BC_S_COND ?
					     entry->sport : entry->dport)) {
				yes = 0;
				break;
			}

			if (cond->prefix_len == 0)
				break;

			if (op->code == INET_DIAG_BC_S_COND)
				addr = entry->saddr;
			else
				addr = entry->daddr;

			if (bitstring_match(addr, cond->addr,
					    cond->prefix_len))
				break;
			if (entry->family == AF_INET6 &&
			    cond->family == AF_INET) {
				if (addr[0] == 0 && addr[1] == 0 &&
				    addr[2] == htonl(0xffff) &&
				    bitstring_match(addr + 3, cond->addr,
						    cond->prefix_len))
					break;
			}
			yes = 0;
			break;
		}
		}

		if (yes) {
			len -= op->yes;
			bc += op->yes;
		} else {
			len -= op->no;
			bc += op->no;
		}
	}
	return (len == 0);
}

static int valid_cc(const void *bc, int len, int cc)
{
	while (len >= 0) {
		const struct inet_diag_bc_op *op = bc;

		if (cc > len)
			return 0;
		if (cc == len)
			return 1;
		if (op->yes < 4)
			return 0;
		len -= op->yes;
		bc  += op->yes;
	}
	return 0;
}

static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
{
	const unsigned char *bc = bytecode;
	int  len = bytecode_len;

	while (len > 0) {
		struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc;

//printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
		switch (op->code) {
		case INET_DIAG_BC_AUTO:
		case INET_DIAG_BC_S_COND:
		case INET_DIAG_BC_D_COND:
		case INET_DIAG_BC_S_GE:
		case INET_DIAG_BC_S_LE:
		case INET_DIAG_BC_D_GE:
		case INET_DIAG_BC_D_LE:
			if (op->yes < 4 || op->yes > len + 4)
				return -EINVAL;
		case INET_DIAG_BC_JMP:
			if (op->no < 4 || op->no > len + 4)
				return -EINVAL;
			if (op->no < len &&